|
--- |
|
license: apache-2.0 |
|
base_model: sshleifer/distilbart-xsum-12-6 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: bart-abs-1409-1829-lr-3e-05-bs-4-maxep-6 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bart-abs-1409-1829-lr-3e-05-bs-4-maxep-6 |
|
|
|
This model is a fine-tuned version of [sshleifer/distilbart-xsum-12-6](https://huggingface.co/sshleifer/distilbart-xsum-12-6) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.8275 |
|
- Rouge/rouge1: 0.3305 |
|
- Rouge/rouge2: 0.1305 |
|
- Rouge/rougel: 0.274 |
|
- Rouge/rougelsum: 0.2747 |
|
- Bertscore/bertscore-precision: 0.8996 |
|
- Bertscore/bertscore-recall: 0.8609 |
|
- Bertscore/bertscore-f1: 0.8797 |
|
- Meteor: 0.2167 |
|
- Gen Len: 22.3 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 3e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 6 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge/rouge1 | Rouge/rouge2 | Rouge/rougel | Rouge/rougelsum | Bertscore/bertscore-precision | Bertscore/bertscore-recall | Bertscore/bertscore-f1 | Meteor | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-----------------------------:|:--------------------------:|:----------------------:|:------:|:-------:| |
|
| 4.3755 | 1.0 | 13 | 3.1954 | 0.2686 | 0.105 | 0.234 | 0.2332 | 0.892 | 0.8445 | 0.8675 | 0.1558 | 14.9 | |
|
| 2.9381 | 2.0 | 26 | 2.8333 | 0.3263 | 0.177 | 0.2735 | 0.2724 | 0.9256 | 0.8588 | 0.8908 | 0.2038 | 16.5 | |
|
| 2.1267 | 3.0 | 39 | 2.6556 | 0.2982 | 0.1563 | 0.2503 | 0.2501 | 0.9117 | 0.852 | 0.8807 | 0.1788 | 16.1 | |
|
| 1.6397 | 4.0 | 52 | 2.6959 | 0.3599 | 0.1731 | 0.3065 | 0.3053 | 0.9095 | 0.8654 | 0.8867 | 0.2624 | 21.2 | |
|
| 1.3337 | 5.0 | 65 | 2.7752 | 0.3542 | 0.1423 | 0.2993 | 0.2987 | 0.9082 | 0.8681 | 0.8876 | 0.2339 | 23.7 | |
|
| 1.1196 | 6.0 | 78 | 2.8275 | 0.3305 | 0.1305 | 0.274 | 0.2747 | 0.8996 | 0.8609 | 0.8797 | 0.2167 | 22.3 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
